MTR

Mass Transit Railway (Hong Kong)

The Mass Transit Railway (MTR) is a major public transport network serving Hong Kong. Operated by the MTR Corporation Limited (MTRCL), it consists of heavy rail, light rail, and feeder bus service centred on an 11-line rapid transit network serving the urbanised areas of Hong Kong Island, Kowloon, and the New Territories. The system included 230.9 km (143.5 mi) of rail in 2018 with 163 stations, including 95 heavy rail stations and 68 light rail stops. The MTR is one of the most profitable metro systems in the world; it had a farebox recovery ratio of 187 per cent in 2015, the world's highest. The MTR was ranked the number one metro system in the world by CNN in 2017.

The MTR partnership started in January 2013 and ended in December 2019 with near capacity operations informed by big transit data analytics as its central theme. Through this partnership, MTR used the Transit Lab’s vast expertise to develop solutions that support MTR’s growth and ability to provide innovative services to its customers. The broad goal was to gain a better understanding of how the MTR system operates at “near capacity” and investigate means of dealing with capacity constraints more effectively, mitigating the impacts. Data from various sources, supported by appropriate models, are used to provide insights into system operations taking a customer-centric view. Examples of the research areas include:
1. Estimation of denied boarding due to capacity constraints and station crowding. The model has replaced expensive, manual surveys that MTR used to conduct several times a year to collect this information.
2. Network performance tools that evaluate system performance, measured by various metrics, under different operating conditions and used for schedule design, and analysis of dispatching strategies.
3. Design, evaluation, and monitoring of transit travel demand management strategies in the form of promotions that encourage behavior shifts away from peak periods.
4. Advanced visualization capabilities that provide valuable insights to managers.
5. Predictive analytics of station and OD demands, as well as expected denied boarding, used to proactively deal with crowd management, respond to incidents, and provide more individualized customer information.

Under this research the MIT-NU team also developed a number of tools related to the above areas that are currently adopted and used in daily operations.

Featured Projects

Public Transportation

Personalized Customer Information and Customer Segmentation

Information has long been recognized as an important instrument for behavioral change. However, generic information provision often proves ineffective. This project aims to develop a framework toward individualized information provision to MTR users. Effective personalization includes three components: Sparse use of information; Deep Customization; Data Infrastructure and Predictive Analytics. One methodological component is the demand prediction at the individualized customer level. The research will develop the general requirements for provision of individualized customer information, evaluate technological alternatives for the communication of information, and design potential experiments to evaluate their effectiveness. Customer segmentation will be used as the means for better understanding different passenger groups and their information needs.

Public Transportation

Tools for Evaluating Future Operations and Design of Demand Management

With the future expansion of the network there is a need for better tools to answer what if operating questions and design and evaluate strategies to deal with disruptions, increases in demand, etc. This activity will build capabilities, based on commercial tools, to evaluate alternatives operating strategies, and strategies to mitigate and relieve system congestion, either recurrent or due to incidents.

Public Transportation

Passenger Assignment to Journeys

The research is looking into the problem of assigning individual passengers to train trips. A probabilistic model utilizing detailed AFC and train movement data is under development, incorporating capacity constraints of individual vehicles. The model estimates the probability that a given passenger boarded a specific train itinerary and the probability of being denied boarding. Such a model can be used for the assessment of the capacity utilization of the system, development of detailed performance metrics from the passengers’ point of view (for example, crowding), identification of individual journey time components, and estimation of the (expected) number of passengers denied boarding, as well information that can used by travel planners.

Featured Publications

Train

Capacity-Constrained Network Performance Model for Urban Rail Systems

Authors:

Baichuan Mo, Zhengliang Ma, Haris N. Koutsopoulos and Jinhua Zhao

Journal:

Transportation Research Record

Date:

2020

This paper proposes a general Network Performance Model (NPM) for urban rail systems performance monitoring using smart card data. NPM is a schedule-based network loading model with strict capacity constraints and boarding priorities. It distributes passengers over the network given origin-destination (OD) demand, operations, route choice, and effective train capacity. A Bayesian simulation-based optimization method for calibrating the effective train capacity is introduced, which explicitly recognizes that capacity may be different at different stations depending on congestion levels. Case studies with data from the Mass Transit Railway (MTR) network in Hong Kong are used to validate the model and illustrate its applicability. NPM is validated using left behind survey data and exit passenger flow extracted from smart card data. The use of NPM for performance monitoring is demonstrated by analyzing the spatial-temporal crowding patterns in the system and evaluating dispatching strategies.

Google Scholar
Train

Optimal Design of Promotion Based Demand Management Strategies in Urban Rail Systems

Authors:

Zhenliang Ma and Haris N. Koutsopoulos

Journal:

Transportation Research Part C

Date:

2019

Travel demand management (TDM) is used for managing congestion in urban areas. While TDM is well studied for car traffic, its application in transit is still emerging. Well-structured transit TDM approaches can help agencies better manage the available system capacity when the opportunity and investment to expand are limited. However, transit systems are complex and the design of a TDM scheme, deciding when, where, and how much discount or surcharge is implemented, is not trivial. The paper proposes a general framework for the optimal design of promotion based TDM strategies in urban rail systems. The framework consists of two major components: network performance and optimization. The network performance model updates the origin-destination (OD) demand based on the response to the promotion strategy, assigns it to the network, and estimates performance metrics. The optimization model allocates resources to maximize promotion performance in a cost effective way by better targeting users whose behavioral response to the promotion improves system performance. The optimal design of promotion strategies is facilitated by the availability of smart card (automated fare collection, AFC) data. The proposed approach is demonstrated with data from a busy urban rail system. The results illustrate the value of the method, compare the effectiveness of different strategies, and highlight the limits of the effectiveness of such strategies.

Google Scholar
Train

Inferring Left Behind Passengers in Congested Metro Systems from Automated Data

Authors:

Yiwen Zhu, Haris N. Koutsopoulos and Nigel H.M. Wilson

Journal:

Transportation Research Part C

Date:

2018

With subway systems around the world experiencing increasing demand, measures such as passengers left behind are becoming increasingly important. This paper proposes a methodology for inferring the probability distribution of the number of times a passenger is left behind at stations in congested metro systems using automated data. Maximum likelihood estimation (MLE) and Bayesian inference methods are used to estimate the left behind probability mass function (LBPMF) for a given station and time period. The model is applied using actual and synthetic data. The results show that the model is able to estimate the probability of being left behind fairly accurately.

Google Scholar
Train

A Probabilistic Passenger-to-Train Assignment Model based on Automated Data

Authors:

Yiwen Zhu, Haris N. Koutsopoulos and Nigel H.M. Wilson

Journal:

Transportation Research Part B

Date:

2017

The paper presents a methodology for assigning passengers to individual trains using: (i) fare transaction records from Automatic Fare Collection (AFC) systems and (ii) Automatic Vehicle Location (AVL) data from train tracking systems. The proposed Passenger-to-Train Assignment Model (PTAM) is probabilistic and links each fare transaction to a set of feasible train itineraries. The method estimates the probability of the passenger boarding each feasible train, and the probability distribution of the number of trains a passenger is unable to board due to capacity constraints. The access/egress time distributions are important inputs to the model. The paper also suggests a maximum likelihood approach to estimate these distributions from AFC and AVL data. The methodology is applied in a case study with data from a major, congested, subway system during peak hours. Based on actual AFC and train tracking data, synthetic data was generated to validate the model. The results, both in terms of the trains passengers are assigned to and train loads, are similar to the "true" observations from the synthetic data. The probability of a passenger being left behind (due to capacity constraints) in the actual system is also estimated by time of day and compared with survey data collected by the agency at the same station. The left behind probabilities can be accurately estimated from the assignment results. Furthermore, it is shown that the PTAM output can also be used to estimate crowding metrics at transfer stations.

Google Scholar

Students

Baichuan Mo

PhD Student

Baichuan is a graduate student in the Interdepartmental Ph.D. in Transportation program at MIT. Prior to join MIT, he got a B.S. degree from Dept. of Civil Engineering, Tsinghua University in Beijing, awarded with the Tsinghua supreme scholarship (10 out of 3000+ undergraduates). Baichuan’s main research interest is data-driven transportation modeling and demand modeling. His current research focuses on Network Performance Modelling and Bayesian Individual Mobility Prediction base for MTR (Hong Kong).  Outside of school, Baichuan enjoys jogging and cooking.